© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194694
    Prev
    Next
    INDEX
    Explanations

    Utils and StringUtils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    外
    0.91
    ي
    0.79
    上
    0.79
    to
    0.77
    र
    0.73
    今年
    0.73
     семь
    0.72
    ב
    0.72
     fervor
    0.71
    这
    0.71
    POSITIVE LOGITS
    ри
    0.94
    ick
    0.84
    0
    0.84
    4
    0.82
    OM
    0.79
    ELO
    0.77
    AM
    0.76
    URF
    0.75
    ם
    0.74
    AL
    0.74
    Activations Density 0.000%

    No Known Activations